© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 23124
    Prev
    Next
    INDEX
    Explanations

    names or references to various organizations or businesses with "Co" in their name

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "Co" in relation to companies or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essage
    -0.72
    speech
    -0.71
    imens
    -0.69
    bath
    -0.63
    sed
    -0.62
    anted
    -0.61
    20439
    -0.60
    ultimate
    -0.60
    esome
    -0.60
     Naj
    -0.60
    POSITIVE LOGITS
     Co
    3.60
    Co
    2.23
     Company
    1.79
    co
    1.71
     co
    1.69
     CO
    1.60
     Cooperation
    1.40
     Cooperative
    1.39
    CO
    1.37
     Corp
    1.13
    Activations Density 0.013%

    No Known Activations